AlKadhum Journal of Science
Not a member yet
50 research outputs found
Sort by
Cognitive Honeypots AI-Enhanced Deception for Proactive Threat Hunting
No full textThe rapidly increasing complexity of cyber threats, including AI-powered attacks, is forcing a shift in defense strategies from reactive to proactive approaches. Traditional honeypots remain largely static and easily identifiable, while newer AI-enhanced models emphasize realism but still lack deep understanding of attacker cognition. To address this gap, this paper introduces CogniTrap, a novel framework that combines a high-interaction honeypot with an AI-driven cognitive deception engine. CogniTrap dynamically creates and adapts “cognitive decoys” designed to exploit attackers’ biases and reasoning flaws. A prototype of CogniTrap was developed and deployed, where decoy placements and adaptations were optimized using reinforcement learning informed by live analysis of attacker tactics, techniques, and procedures (TTPs). Intelligence gathered from triggered decoys was transformed into proactive hypotheses for threat hunting in production environments. Experimental results from comparative 30-day live deployments showed that CogniTrap increased attacker dwell time by 45% compared to a standard high-interaction honeypot and generated higher interaction rates with deceptive assets. Furthermore, it was able to produce high-fidelity threat hunting queries based on attacker cognitive patterns, validating its practical utility. This research marks the first implementation-based framework for adaptive cognitive honeypots, bridging the gap between theoretical cognitive security concepts and operational proactive threat hunting. By providing architecture, algorithms, and empirical validation, CogniTrap establishes a new paradigm for intelligent cyber defense
Federated Learning for Early Detection of Advanced Persistent Threats in IoT Networks
No full textIn the era of connected IoT devices, ensuring cybersecurity while preserving data privacy is increasingly critical. Federated learning offers a promising approach by enabling collaborative training of detection systems without sharing raw data. This paper presents a novel federated Intrusion Detection System (IDS) based on XGBoost algorithm, and for the first time designed to detect initial compromise (I.C.) phase of Advanced Persistent Threats (APTs) in distributed Internet of Things (IoT) environments. By leveraging the federated framework, the IDS achieves robust detection across multiple devices while maintaining privacy and minimizing computational overhead. Extensive simulation results indicated that our proposed method achieved a precision of 97%, recall of 100%, and F1-score of 98%, providing a practical and efficient solution for real-world IoT security challenges
Deep Learning-Based Blood Cell Classification with Enhanced Data Preprocessing and Augmentation
No full textClassification of blood cells accurately is an extremely important task in the field of hematology, for the diagnosis of blood disorders and for guiding decision making in the clinical context. In this paper, we use a high-quality dataset of 17,092 microscopic peripheral blood cell images from the Hospital Clinic of Barcelona, encompassing eight different cell types, all of which have been annotated by expert pathologists. To improve model performance and to tackle the class imbalance in the dataset, we developed a strong data preprocessing and data augmentation pipeline which includes contrast enhancement, normalization, geometric and photometric transformations, injection of noise, and mixup style synthetic data. We develop two state-of-the-art deep learning models (EfficientNet-B0, ResNet50) to enable benchmarking of the proposed pipeline. In our experimental results, EfficientNet-B0 achieved overall accuracy of approximately 98.3% and ResNet50 achieved accuracy of 98.6%, with very good precision, recall, and F1-scores for all classes. These preliminary results demonstrate the effectiveness of the designed data preprocessing and data augmentation strategies, as well as provide a benchmark for managing blood cell images in hematology for future research.
 
A Comprehensive Framework for Quality Assurance of Generative AI Text: Comprehensive Framework for Quality Assurance of Generative AI Text
No full textThis paper presents a comprehensive framework for the quality assurance (QA) of text outputs generated by artificial intelligence (AI) models. The framework incorporates multiple metrics to evaluate the generated text, including grammar and spelling correctness, relevance to the prompt, and linguistic diversity. The proposed method employs the Python library language for grammatical error detection, TF-IDF vectorization coupled with cosine similarity for relevance assessment, and NLTK for measuring lexical diversity. By integrating these metrics, the framework provides a robust mechanism to ensure the generated text meets the desired quality standards. This approach is demonstrated through a sample implementation in Python, which can be easily extended and customized for various applications in generative AI
Pepper Leaf Disease Detection Using Deep Learning Techniques
No full textEarly diagnosis of pests and plant diseases is crucial for preventing significant crop losses. This study proposes a leaf disease detection system using MobileNetV2 integrated with multiple optimization techniques (Adam and learning rate scheduling). Evaluated on the Pepper PlantVillage dataset, the MobileNetV2 model employs patch embedding and attention mechanisms for feature extraction, with SoftMax used for final classification. The model was further validated on a multi-class Apple PlantVillage dataset. Results demonstrate high accuracy: 97.03% for pepper and 94.63% for apple classification. Comparative analysis with CNN architectures shows superior efficiency and faster convergence for our model, outperforming Inception v3 (96.81%) and VGG-19 (94.93%) on the pepper dataset
Practical Implementation and Analysis of Software Metrics Impact on Maintainability in Open-Source Systems
No full textCommon software metrics and maintainability measures in open-source Java are examined in this research.The authors test the major object-oriented metrics—Coupling Between Objects (CBO), Lines of Code (LOC), Weighted Methods per Class (WMC), Lack of Cohesion of Methods (LCOM), Depth of Inheritance Tree (DIT), and Cyclomatic Complexity—against real-world maintainability indicators like bug counts, code modifications, and developer turnover. The authors use Python data analysis and visualization to find statistically significant patterns in Spearman correlation analysis.
The findings indicate that metrics such as CBO and cyclomatic complexity are very predictive in terms of maintenance effort, whereas others, such as DIT, provide little insight. In addition to theoretical justification, this work provides a practical, reproducible workflow to be implemented by software engineers to give priority to code quality and make more intelligent maintenance decisions. Finally, this study ties the strengths of academic measures and the real-world aspects of daily software engineering.
 
Hybrid PSO-Bagging Approach for Efficient and Accurate Network Anomaly Detection
No full textThe surge in internet usage has triggered a substantial increase in network attacks, raising serious cyber security concerns. Fog computing, which enhances cloud computing by providing low-latency services to mobile users, is particularly susceptible to these threats due to its proximity to end users and limited computational resources. Traditional Intrusion Detection Systems (IDS) designed for conventional networks may not directly apply to fog computing environments, where the ability to process and analyze large volumes of data efficiently is crucial. This paper presents a novel approach for network anomaly detection within fog environments, utilizing a Particle Swarm Optimization (PSO) -based Wrapper feature selection method combined with the Bagging technique. By applying this methodology to the NSL-KDD dataset, our approach effectively reduces computational complexity and improves the accuracy of intrusion detection models. The proposed system demonstrates superior performance compared to existing methods, achieving an impressive 98.3% accuracy and a low false positive rate of 1.5%. These results underscore the potential of the PSO-Bagging framework to enhance the security of fog computing systems, offering a robust solution to the growing problem of network attacks in distributed computing environments
Security Content Used To Protect Data From Social Media
No full textAbstract
Social media networks have revolutionized global connectivity, enabling billions of users to engage in virtual communities and mutual interactions. However, their widespread adoption has attracted malicious actors who exploit platform vulnerabilities to compromise user security and privacy. Despite preventive measures, cyber-attacks targeting social media have surged, necessitating advanced intrusion detection systems (IDS) to mitigate risks. Although these platforms fetch never-seen convenience, users do not have the technical ability to understand the privacy implications of their shared content. As a result the use of available privacy settings fall short compared to the general practice of security. This study initiates the development of a holistic framework for social media security that integrates
Policy-driven safeguards: Use strong passwords, keep updating your credentials often, share data carefully, use antivirus software, and stick to your own software.
Artificial Intelligence (AI) and Machine Learning (ML)-driven solutions:: Machine learning algorithms for user sentiment analysis, disinformation detection, combating illicit activities such as child trafficking, and adversarial machine learning-based enhancement of intrusion detection.
Ethical AI integration: Aligning with "AI for Good" efforts can help cut down biases and ensure fairness in automated security setups.
The paper takes a close look at the latest improvements in social media security, stressing how important it is to protect private information as more breaches happen that could harm economic stability and confidence in using these platforms. This helps connect tech creativity with strict rules and offers a new way to strengthen platform trustworthiness and ability to bounce back in a digital world that is becoming more competitive.
Analyzing Big Data to Mitigate Cyber Attacks Using Machine Learning Classifications: A Comparative Study of an Efficient Classifier Set
No full textIn this research, we address a set of methodological approaches and approaches in scientific research in the field of cybersecurity and big data analysis using machine learning techniques, which have made the data analysis process easier to understand and mitigate cyberattacks. This method involves data processing and analysis in a series of stages, or in the form of analytical protection layers, including analysis and organization of large databases,. Training and qualifying classifiers is a method for reducing the dimensionality and skewness of feature vectors according to basic procedure analysis.. Using the principal components in the analysis, we employ various binary classifiers for vector K-nearest neighbors and many other algorithms, such as Bayesian algorithms and others, analyze vector machines, as well as artificial intelligence, which work to increase the efficiency and accuracy of attack detection devices. Artificial neural networks are also highly efficient in detecting cyberattacks and analyzing all network disturbances. Through our research, the basic idea was to classify and segment data and deal with each type of data separately to facilitate processing. Another approach is to combine data classifiers. This idea relies on two options: soft voting and majority voting. Each approach has its own method and method for specific use. methods for intrusion detection and penetration of large databases. In the first approach, we analyze and process data in parallel by classifying and dividing it into several subsets, and assigning each subset a separate path. In this method, we partition the problem, making the solution simpler and the data less complex. In the other approach, we also use sensors to collect client data within search servers. The sensor contains a set of parallel paths, each path analyzes the data and information for the client, and is conducted through a parallel network that detects anomalies through two different data sets. One group contains computer network traffic, which includes examining data and hosts from distributed denial of service (DDOS) attacks. The other group contains the Internet of Things and its data
Fake News Detection: A Comprehensive Taxonomy of Text, Image, Video, and Multi-Modal Techniques
No full textThe widespread dissemination of fake news across digital platforms has posed significant challenges for information integrity, social stability, and public trust. Traditional fake news detection approaches, primarily based on text analysis, are no longer sufficient, as misinformation now integrates multi-modal content, including images, videos, and manipulated metadata. This paper presents a comprehensive taxonomy of fake news detection techniques, categorizing existing methods into text-based, image-based, video-based, and multi-modal approaches. We review the evolution of detection methodologies, from traditional machine learning models to advanced deep learning architectures, including transformers, convolutional neural networks (CNN), and hybrid AI models. Additionally, we analyze the growing challenge of adversarial attacks, where malicious actors manipulate text, images, and videos to bypass detection systems. Finally, we highlight emerging research directions, such as adversarial-resilient AI models, cross-modal fact verification, and human-AI hybrid fact-checking systems, which are crucial for developing trustworthy, explainable, and robust fake news detection frameworks. This study serves as a foundation for researchers and practitioners in advancing multi-modal misinformation detection and strengthening AI-driven fact-checking mechanisms